Default to streaming mode

config/charts/inferencepool/README.md

@@ -5,17 +5,27 @@ A chart to deploy an InferencePool and a corresponding EndpointPicker (epp) depl
 
 ## Install
 
-To install an InferencePool named `pool-1`  that selects from endpoints with label `app: vllm-llama2-7b` and listening on port `8000`, you can run the following command:
+To install an InferencePool named `vllm-llama2-7b`  that selects from endpoints with label `app: vllm-llama2-7b` and listening on port `8000`, you can run the following command:
 
 ```txt
-$ helm install pool-1 ./config/charts/inferencepool \
-  --set inferencePool.name=pool-1 \
+$ helm install vllm-llama2-7b ./config/charts/inferencepool \
+  --set inferencePool.name=vllm-llama2-7b \
   --set inferencePool.selector.app=vllm-llama2-7b \
   --set inferencePool.targetPortNumber=8000
 ```
 
 where `inferencePool.targetPortNumber` is the pod that vllm backends served on and `inferencePool.selector` is the selector to match the vllm backends.
 
+To install via the latest published chart in staging  (--version v0 indicates latest dev version), you can run the following command:
+
+```txt
+$ helm install vllm-llama2-7b \
+  --set inferencePool.name=vllm-llama2-7b \
+  --set inferencePool.selector.app=vllm-llama2-7b \
+  --set inferencePool.targetPortNumber=8000 \
+  oci://us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/charts/inferencepool --version v0
+```
+
 ## Uninstall
 
 Run the following command to uninstall the chart:

config/charts/inferencepool/templates/inferencepool.yaml

@@ -49,6 +49,9 @@ spec:
         - "9003"
         - -metricsPort
         - "9090"
+        env:
+        - name: USE_STREAMING
+          value: "true"
         ports:
         - name: grpc
           containerPort: 9002

config/manifests/gateway/patch_policy.yaml

@@ -54,37 +54,37 @@ spec:
         op: replace
         path: "/virtual_hosts/0/routes/0/route/cluster"
         value: original_destination_cluster
-# Uncomment the below to enable full duplex streaming
-    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
-    #   name: "default/inference-gateway/llm-gw"
-    #   operation:
-    #     op: add
-    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_body_mode"
-    #     value: FULL_DUPLEX_STREAMED
-    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
-    #   name: "default/inference-gateway/llm-gw"
-    #   operation:
-    #     op: add
-    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_trailer_mode"
-    #     value: SEND
-    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
-    #   name: "default/inference-gateway/llm-gw"
-    #   operation:
-    #     op: add
-    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_body_mode"
-    #     value: FULL_DUPLEX_STREAMED
-    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
-    #   name: "default/inference-gateway/llm-gw"
-    #   operation:
-    #     op: replace
-    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_trailer_mode"
-    #     value: SEND
-    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
-    #   name: "default/inference-gateway/llm-gw"
-    #   operation:
-    #     op: replace
-    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_header_mode"
-    #     value: SEND
+# Comment the below to disable full duplex streaming
+    - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+      name: "default/inference-gateway/llm-gw"
+      operation:
+        op: add
+        path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_body_mode"
+        value: FULL_DUPLEX_STREAMED
+    - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+      name: "default/inference-gateway/llm-gw"
+      operation:
+        op: add
+        path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_trailer_mode"
+        value: SEND
+    - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+      name: "default/inference-gateway/llm-gw"
+      operation:
+        op: add
+        path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_body_mode"
+        value: FULL_DUPLEX_STREAMED
+    - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+      name: "default/inference-gateway/llm-gw"
+      operation:
+        op: replace
+        path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_trailer_mode"
+        value: SEND
+    - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+      name: "default/inference-gateway/llm-gw"
+      operation:
+        op: replace
+        path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/response_header_mode"
+        value: SEND
 ---
 apiVersion: gateway.envoyproxy.io/v1alpha1
 kind: EnvoyExtensionPolicy

config/manifests/inferencepool.yaml

@@ -56,7 +56,7 @@ spec:
         - "9003"
         env:
         - name: USE_STREAMING
-          value: "false"
+          value: "true"
         ports:
         - containerPort: 9002
         - containerPort: 9003